© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 11702
    Prev
    Next
    INDEX
    Explanations

    locations

    oai_token-act-pair · gpt-3.5-turbo

    locations or places referenced in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apult
    -0.77
    ragon
    -0.71
    sson
    -0.70
    ivot
    -0.69
    mind
    -0.66
    unes
    -0.65
    iets
    -0.64
    ithering
    -0.63
    termin
    -0.63
     Pwr
    -0.62
    POSITIVE LOGITS
    upon
    1.22
    soever
    1.14
     they
    1.06
    abouts
    0.88
     he
    0.85
     she
    0.78
     residents
    0.77
     visitors
    0.76
     we
    0.76
     employees
    0.74
    Activations Density 0.074%

    No Known Activations